Steve Engels
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Steve Engels has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Adam Tindale
Digital Futures, OCAD University, Toronto, Ontario, Canada
1 shared publication - Ana Zdravkovic
Emotions and Learning Optimization Laboratory, Developmental Psychology and Education (DPE), Ontario Institute for Studies in Education (OISE), The University of Toronto, Toronto, ON M5S 1V6, Canada
1 shared publication - Bogdan Pikula
University of Toronto
1 shared publication - Earl Woodruff
Ontario Institute for Studies in Education, University of Toronto, Toronto, ON M5S 1A1, Canada
1 shared publication - Emma Westecott
Digital Futures, OCAD University, Toronto, Ontario, Canada
1 shared publication - Jessica Patel
Digital Futures, OCAD University, Toronto, Ontario, Canada
1 shared publication
Latest Publications
- Open Access
- 17 April 2026
- Published by MDPI AG in Behavioral Sciences
- Vol. 16 (4) , 597
When Anger Strikes: Using AI Modelling to Understand How Negative Emotions Impact Performance in Digital Math Games
Digital game-based learning environments (DGBLEs) are increasingly integrated into classrooms as learning tools, yet limited research exists regarding the impact of students’ discrete emotions on digital gameplay performance. This study examined the role of emotions and arousal in predicting performance outcomes during digital gameplay. Thirty-two grade 5 students (Mage = 10.99, 62.5% male) played four digital games (two math; two identically designed non-math). During gameplay, real-time heart rate and affective data were collected and analyzed using an interpretable machine learning approach (XGBoost). Results suggest that students performed better on non-math games, as compared to math games. Real-time anger was associated with lower performance, particularly in games, whereas other emotions and physiological measures were not significant predictors. This pilot investigation suggests that discrete emotions, particularly anger, may play a more important role in performance during math gameplay than in comparable non-math activities. The results highlight the importance of supporting emotional regulation during digital math learning, as unmanaged anger may impact performance. This study contributes to the growing literature on affective dynamics in digital game-based learning.
- 17 April 2026
- Published by MDPI AG in Behavioral Sciences
- Vol. 16 (4) , 597
Open AccessWhen Anger Strikes: Using AI Modelling to Understand How Negative Emotions Impact Performance in Digital Math Games
Digital game-based learning environments (DGBLEs) are increasingly integrated into classrooms as learning tools, yet limited research exists regarding the impact of students’ discrete emotions on digital gameplay performance. This study examined the role of emotions and arousal in predicting performance outcomes during digital gameplay. Thirty-two grade 5 students (Mage = 10.99, 62.5% male) played four digital games (two math; two identically designed non-math). During gameplay, real-time heart rate and affective data were collected and analyzed using an interpretable machine learning approach (XGBoost). Results suggest that students performed better on non-math games, as compared to math games. Real-time anger was associated with lower performance, particularly in games, whereas other emotions and physiological measures were not significant predictors. This pilot investigation suggests that discrete emotions, particularly anger, may play a more important role in performance during math gameplay than in comparable non-math activities. The results highlight the importance of supporting emotional regulation during digital math learning, as unmanaged anger may impact performance. This study contributes to the growing literature on affective dynamics in digital game-based learning.
- Open Access
- 13 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 23-29
Combatting Toxicity: Early Designs of an Intelligent In-Game Intervention System for Verbal Harassment
- 13 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 23-29
Open AccessCombatting Toxicity: Early Designs of an Intelligent In-Game Intervention System for Verbal Harassment
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 741-742
Enhancing MIPS Assembly Language Education with Saturn
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 741-742
Open AccessEnhancing MIPS Assembly Language Education with Saturn
- Open Access
- 6 October 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Vol. 19 (1) , 337-342
FlexComb: A Facial Landmark-Based Model for Expression Combination Generation
Facial expressions are a crucial but challenging aspect of animating in-game characters. They provide vital nonverbal communication cues, but given the high complexity and variability of human faces, the task of capturing the natural diversity and affective complexity of human faces can be a labour-intensive process for animators. This motivates the need for more accurate, realistic and lightweight methods for generating emotional expressions for in-game characters. In this work, we introduce FlexComb, a Facial Landmark-based Expression Combination model, designed to generate a real-time space of realistic facial expression combinations. FlexComb leverages the highly varied CelebV-HQ dataset containing emotions in the wild, and a transformer-based architecture. The central component of the FlexComb system is an emotion recognition model that is trained on the facial dataset, and used to generate a larger dataset of tagged faces. The resulting system generates in-game facial expressions by sampling from this tagged dataset, including expressions that combine emotions in specified amounts. This allows in-game characters to take on variety of realistic facial expressions for a single emotion, which addresses this primary challenge of facial emotion modeling. FlexComb shows potential for expressive facial emotion simulation with applications that include animation, video game development, virtual reality, and human-computer interaction.
- 6 October 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Vol. 19 (1) , 337-342
Open AccessFlexComb: A Facial Landmark-Based Model for Expression Combination Generation
Facial expressions are a crucial but challenging aspect of animating in-game characters. They provide vital nonverbal communication cues, but given the high complexity and variability of human faces, the task of capturing the natural diversity and affective complexity of human faces can be a labour-intensive process for animators. This motivates the need for more accurate, realistic and lightweight methods for generating emotional expressions for in-game characters. In this work, we introduce FlexComb, a Facial Landmark-based Expression Combination model, designed to generate a real-time space of realistic facial expression combinations. FlexComb leverages the highly varied CelebV-HQ dataset containing emotions in the wild, and a transformer-based architecture. The central component of the FlexComb system is an emotion recognition model that is trained on the facial dataset, and used to generate a larger dataset of tagged faces. The resulting system generates in-game facial expressions by sampling from this tagged dataset, including expressions that combine emotions in specified amounts. This allows in-game characters to take on variety of realistic facial expressions for a single emotion, which addresses this primary challenge of facial emotion modeling. FlexComb shows potential for expressive facial emotion simulation with applications that include animation, video game development, virtual reality, and human-computer interaction.